Update deepspeed.yaml

.github/workflows/deepspeed.yaml

@@ -88,63 +88,24 @@ jobs:
 
         ds_report
 
-    - id: setup-venv
-      uses: ./DeepSpeed/.github/workflows/setup-venv
+    - name: Retry Step
+      uses: nick-fields/retry@v3
+      with:
+        timeout_seconds: 15
+        max_attempts: 3
+        retry_on: error
 
     - name: Python environment
       run: |
         source /root/.bashrc
         pip list
 
-    - name: PyTorch Lightning Tests
-      run: |
-        unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
-        pip install pytorch-lightning
-        pip install "protobuf<4.21.0"
-        cd DeepSpeed/tests
-        pytest $PYTEST_OPTS lightning/
-      continue-on-error: true
-
-    - name: MII unit tests
-      run: |
-        BRANCH="main"
-        if [[ ! -z "${{ github.event.inputs.mii_branch }}" ]]; then
-            BRANCH="${{ github.event.inputs.mii_branch }}"
-        fi
-        echo "Cloning DeepSpeed-MII branch: $BRANCH"
-        git clone -b $BRANCH --depth=1 https://github.com/microsoft/DeepSpeed-MII.git
-        cd DeepSpeed-MII
-        pip install .[dev]
-        unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
-        cd tests/legacy
-        pytest $PYTEST_OPTS --forked -m "deepspeed" ./
-      continue-on-error: true
-
-    - name: HF Accelerate tests
-      run: |
-        unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
-        git clone https://github.com/huggingface/accelerate
-        cd accelerate
-        git rev-parse --short HEAD
-        # installing dependencies
-        pip install .[testing]
-        # force protobuf version due to issues
-        pip install "protobuf<4.21.0"
-        # tmp fix: force newer datasets version
-        #pip install "datasets>=2.0.0"
-        pip list
-        pytest $PYTEST_OPTS --color=yes --durations=0 --verbose tests/deepspeed
-      continue-on-error: true
-
     - name: Unit tests
       run: |
         source /root/.bashrc
         unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
-        
         cd DeepSpeed/tests/unit/
-        # pytest --verbose $PYTEST_OPTS --forked -n 4  unit/
-        # pytest $PYTEST_OPTS --forked -m 'sequential' unit/
-
+        
         pytest --verbose accelerator/*
         pytest --verbose autotuning/*
         pytest --verbose checkpoint/test_reshape_checkpoint.py